Lightnews — Scholar-powered news

Reposted by Mike Dereviannykh

Valentin Deschaintre @vdeschaintre.bsky.social · Aug 13

I will be presenting in the 10.30 session in room 208-209. I will share thoughts about implicit/generative and explicit appearance representations. See you there if that sounds interesting!

Valentin Deschaintre @vdeschaintre.bsky.social · Aug 8

🧑‍🎓I have the pleasure to present at the Best of Eurographics session at #SIGGRAPH2025 next week! I’ll be looking back at our work on appearance authoring, editing & understanding — come by and say hi! 🔗 s2025.conference-schedule.org/presentation...

Presentation - SIGGRAPH 2025 Conference Schedule

s2025.conference-schedule.org

1 2

Mike Dereviannykh @mishok43.bsky.social · Aug 13

In just less than an hour we'll present "Neural Two-Level Monte Carlo Real-Time Rendering" on SIGGRAPH 2025 at "Best of Eurographics" session

Please join us, it'll be fun! 😊

🏠Room 208-209
🕜10:30-11:30

3

Reposted by Mike Dereviannykh

Christoph Peters @momentsingraphics.bsky.social · Aug 3

Physically-based differentiable rendering enables inverse rendering, but handling visibility is hard. Our SIGGRAPH
2025 paper uses quadrics to importance sample silhouette edges--outperforming all existing unidirectional differentiable path tracers.
momentsingraphics.de/Siggraph2025...

1 7 42

Mike Dereviannykh @mishok43.bsky.social · Jul 28

Done, thank you so much for the info!

1

Mike Dereviannykh @mishok43.bsky.social · Jul 28

And it's a fantastic coincidence that I'm already next to Vancouver and don't need to suffer from jet lag the 2nd time... a horrible thing

1

Mike Dereviannykh @mishok43.bsky.social · Jul 28

Session's time and location for your schedule:
s2025.conference-schedule.org/presentation...

Presentation - SIGGRAPH 2025 Conference Schedule

s2025.conference-schedule.org

Mike Dereviannykh @mishok43.bsky.social · Jul 28

Big news! The Eurographics Association invited us to present our work "Neural Two-Level Monte Carlo Real-Time Rendering" at #SIGGRAPH2025 🎉
Super honored - my first SIGGRAPH!

Let’s discuss neural & real-time rendering, grab a coffee, or just hang out - feel free to leave a DM

2 8

Mike Dereviannykh @mishok43.bsky.social · Jul 26

Just joined RealityLabs at Meta to do some real-time neural rendering research. Unfortunately without a 9- digits compensation package, but WIP 😁

I'm in the Redmond office, but already visited Seattle. If you wanna grab ☕ - DMs are opened

2

Mike Dereviannykh @mishok43.bsky.social · Jun 25

Currently, the issue with efficient spatial encoding is more or less resolved (iNGP or the new GATE by @boksajak.bsky.social )

But it's not the case for the directional domain at all. Despite its importance for the unbiased rendering, Cache-Based Resampling and 2-Level Monte-Carlo Estimator

2

Mike Dereviannykh @mishok43.bsky.social · Jun 25

To be completely honest, it's a equal-time-comparison:

3SPP vs 1SPP+25 Neural Resamples

I believe we should invest more resources in more rapid adaptivity of neural caches and more aggressive quantizations, so we could deliver it to production real-time rendering

1 2

Mike Dereviannykh @mishok43.bsky.social · Jun 25

It's a cool work which deserve a lot attentions from real-time rendering community!

Previously I've got a little bit of time to conduct similar experiments on top of our NIRC, as each additional neural sample costs just pure tensor FLOPs ~ 1.5ms on 4080

1 spp vs 1 spp + 25 cache resamples

1 2

Mike Dereviannykh @mishok43.bsky.social · Jun 25

I found it cool to hear the motivation for High-Frequency Learnable Encoding for NRC\NIRC\Neural Ambient Occlusion from the perspective of Kernel Machines!

Classics 😊

1 5

Mike Dereviannykh @mishok43.bsky.social · Jun 6

Hmmm, 1 min sounds amazing, I didn't expect such speed!

Mike Dereviannykh @mishok43.bsky.social · Jun 4

Congrats to you and to the whole team!

I've got a question: basically the volumetric blocks don't have any transparency, do they? And you rely on pruning to make them look right because of it?

1

Mike Dereviannykh @mishok43.bsky.social · May 17

Thanks 🥳

Reposted by Mike Dereviannykh

Valentin Deschaintre @vdeschaintre.bsky.social · May 13

I was very honoured to receive one of the two Eurographics Young Researcher Award 2025 yesterday!

This is the combination of the work of many people, mentors, collaborators, students, friends who trusted me and taught me so much along the way!

9 4 38

Mike Dereviannykh @mishok43.bsky.social · May 17

Huge congrats, Valentin!

100% Deserved

1 1

Mike Dereviannykh @mishok43.bsky.social · May 16

If you've missed the paper, just check it out:
mishok43.github.io/nirc/

And feel free to reach out to me, if you wanna help me with pushing forward the neural rendering for real-time applications

Neural Two-Level Monte Carlo Real-Time Rendering

Efficient real-time global illumination rendering using Neural Incident Radiance Cache combined with Two-Level Monte Carlo. By Mikhail Dereviannykh, Dmitrii Klepikov, Johannes Hanika, and Carsten Dach...

mishok43.github.io

Mike Dereviannykh @mishok43.bsky.social · May 16

We've received an "Honorable Mention" at the Eurographics 2025 for our work on "Neural Two-Level Monte Carlo Real-Time Rendering" in London! 🥳

Huge thanks to everyone who supported me along the way, and to the EG chairs, committee, and organizers for this recognition

1 4

Mike Dereviannykh @mishok43.bsky.social · May 15

That's what I mean by the lack of compute

Mike Dereviannykh @mishok43.bsky.social · May 15

If you're interested in something like AlphaEvolve but focused on CG, GameDev, or offline rendering, feel free to reach out. I’ve been leading research in this space with strong results so far.

But we need support with compute, expertise and even maybe with engineering

Matej Balog @matejbalog.bsky.social · May 14

Announcing AlphaEvolve, our new LLM coding agent that has
- made new scientific discoveries
- discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design & data centers)

Blog: deepmind.google/discover/blo...
White paper:
storage.googleapis.com/deepmind-med...

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators

deepmind.google

1 1

Mike Dereviannykh @mishok43.bsky.social · May 11

And of course, huge thanks to my amazing co-authors — Dmitrii Klepikov, Johannes Hanika, Carsten Dachsbacher — and industry friends @kaplanyan.bsky.social , Sebastian Herholz, @momentsingraphics.bsky.social, who helped me on the way!

1

Mike Dereviannykh @mishok43.bsky.social · May 11

But there are so many other cool questions that we tried to cover

So please check out our webpage, demo videos, and paper itself: mishok43.github.io/nirc/

📍I’ll be at Eurographics next week in London — if you're around and want to talk rendering, AI, or just grab coffee, DM me!

Neural Two-Level Monte Carlo Real-Time Rendering

Efficient real-time global illumination rendering using Neural Incident Radiance Cache combined with Two-Level Monte Carlo. By Mikhail Dereviannykh, Dmitrii Klepikov, Johannes Hanika, and Carsten Dach...

mishok43.github.io

1 1

Mike Dereviannykh @mishok43.bsky.social · May 11

In equal-time comparisons, NIRC achieves surprisingly cool results both in the biased and unbiased cases

But yeah... variance may increase next to foliage, brush, trees🌿 — still the eternal pain in CG 😅

1

Mike Dereviannykh @mishok43.bsky.social · May 11

Using Two-Level Monte Carlo, we can debias NIRC while still cutting variance — thanks to fast cache sampling - dozens of times for the cost of 1 real path

It works like (N)CV, but doesn't introduce any architectural constraints! No need to train Normalizing Flows on-the-fly

1 1